© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7962
    Prev
    Next
    INDEX
    Explanations

    terms related to analysis and evaluation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    close inspection

    np_acts-logits-general · gemini-2.0-flash

    review and examine carefully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oredCriteria
    -0.80
     réus
    -0.58
    észetes
    -0.57
    VersionUID
    -0.57
     betweenstory
    -0.55
    ///</
    -0.54
     насељу
    -0.54
     temporaire
    -0.54
     Мексичка
    -0.53
    makeText
    -0.52
    POSITIVE LOGITS
     carefully
    1.60
     closely
    1.49
     thoroughly
    1.47
    caref
    1.25
     intently
    1.18
     Carefully
    1.09
     cuidadosamente
    1.08
     intensively
    1.06
     attentively
    1.02
     minutely
    1.00
    Activations Density 0.427%

    No Known Activations